CN115288950A

CN115288950A - Wind power fan monitoring method, device and system and computer readable storage medium

Info

Publication number: CN115288950A
Application number: CN202210976832.1A
Authority: CN
Inventors: 李颖杰; 胡磊; 银磊
Original assignee: Shenzhen Liangyun Energy Network Technology Co ltd; China Power Investment Hubei Jieling Wind Power Generation Co ltd
Current assignee: China Power Investment Hubei Xianjuding Wind Power Generation Co ltd; Shenzhen Liangyun Energy Network Technology Co ltd
Priority date: 2022-08-15
Filing date: 2022-08-15
Publication date: 2022-11-04

Abstract

The invention discloses a wind power fan monitoring method, a device and a system and a computer readable storage medium, wherein the method comprises the following steps: and (4) classification: when a starting instruction is detected, acquiring target data through a sensor and a data acquisition unit which are installed in advance, and classifying the target data to obtain a classification result; a monitoring step: inputting the target data into a corresponding monitoring model according to the classification result, and combining the monitoring model with a pre-established wind power fan digital twin body to obtain a monitoring result; a display step: and displaying the monitoring result based on the wind power fan digital twin body. According to the invention, the target data is acquired through the pre-installed sensor and the data acquisition unit, the target data is classified and input into the corresponding monitoring model, the monitoring result is obtained through the corresponding monitoring model and the wind power fan digital twin body, and the accuracy of abnormal monitoring of the wind power fan is improved.

Description

Wind power fan monitoring method, device and system and computer readable storage medium

Technical Field

The invention relates to the technical field of wind power, in particular to a wind power fan monitoring method, device and system and a computer readable storage medium.

Background

Along with the increasing awareness of environmental protection, the use of clean energy is more and more popular, and wind power generation is the most representative of clean energy; wind power generation is through converting wind energy into the kinetic energy of blade through wind-powered electricity generation fan to kinetic energy with the blade converts the electric energy into, because wind-powered electricity generation fan is at outdoor work, receive the influence of environment very easily and go on appearing unusually, the monitoring of present most wind-powered electricity generation fans is through artifical the going on, perhaps obtains certain data characteristic when wind-powered electricity generation fan moves through the sensor, and then judges whether wind-powered electricity generation fan takes place unusually, and wind-powered electricity generation fan is a complicated structure, often can not accurately monitor wind-powered electricity generation fan near manual work or single data and whether unusually takes place.

Therefore, how to improve the accuracy of the abnormal monitoring of the wind power fan is a problem which needs to be solved urgently.

Disclosure of Invention

The invention mainly aims to provide a wind power fan monitoring method, device and system and a computer readable storage medium, and aims to solve the problem of how to improve the accuracy of wind power fan monitoring.

In order to achieve the above object, the present invention provides a wind power fan monitoring method, which comprises the following steps:

and (3) classification step: when a starting instruction is detected, acquiring target data through a sensor and a data acquisition unit which are installed in advance, and classifying the target data to obtain a classification result;

a monitoring step: inputting the target data into a corresponding monitoring model according to the classification result, and combining the monitoring model with a pre-established wind power fan digital twin body to obtain a monitoring result;

a display step: and displaying the monitoring result based on the wind power fan digital twin body.

Optionally, the sensor comprises: install sound, vibration and temperature integral type sensor in the driving chain of wind-powered electricity generation fan, install sound, vibration and temperature integral type sensor of the blade root of wind-powered electricity generation fan, install shake degree sensor and the angular transducer on the tower section of thick bamboo top of wind-powered electricity generation fan and install the angular transducer in the tower section of thick bamboo bottom, categorised step includes:

and a transmission chain and blade data acquisition sub-step: collecting sound data, vibration data and temperature data of the transmission chain and the blades through the sound, vibration and temperature integrated sensor;

a tower data acquisition substep: acquiring shaking data of the tower drum through the shaking degree sensor, and acquiring inclination data of the tower drum through the inclination angle sensor;

determine target data sub-step: collecting a working condition data set and environment data of the wind power fan through a data collector, and combining the sound data, the vibration data, the temperature data, the shaking data and the inclination data to obtain target data.

Optionally, the monitoring model comprises: drive chain monitoring model, blade monitoring model and tower section of thick bamboo monitoring model, the monitoring step includes:

drive chain monitoring substep: according to the classification result, inputting the environment data, the transmission chain working condition data in the working condition data set, and the sound data, the vibration data and the temperature data of the transmission chain into the transmission chain monitoring model, and combining the transmission chain monitoring model with a pre-established wind power fan digital twin body to obtain a transmission chain monitoring result;

a blade monitoring sub-step: inputting the environmental data, the blade working condition data in the working condition data set, and the sound data, the vibration data and the temperature data of the blade into the blade monitoring model, and combining the pre-created wind power fan digital twin body through the blade monitoring model to obtain a blade monitoring result;

a tower barrel monitoring substep: and inputting the environment data, the working condition data set and the shaking data and the inclination data of the tower drum into the tower drum monitoring model, and combining the tower drum monitoring model with a pre-established wind power fan digital twin body to obtain a tower drum monitoring result.

Optionally, the drive train monitoring sub-step comprises:

and (3) inputting a transmission chain monitoring model: inputting the environment data, the working condition data of the transmission chain, and the sound data, the vibration data and the temperature data of the transmission chain into the transmission chain monitoring model;

calculating a time domain characteristic value: generating a corresponding time domain oscillogram according to the vibration data of the transmission chain through the transmission chain monitoring model, and calculating a time domain characteristic value corresponding to the vibration data of the transmission chain according to the time domain oscillogram;

comparing the characteristic values: generating a simulation time domain characteristic value of the transmission chain according to the environment data and the transmission chain working condition data by combining the transmission chain monitoring model with the wind power fan digital twin body, and comparing the time domain characteristic value with the simulation time domain characteristic value;

and (3) obtaining a transmission chain monitoring result: and if the time domain characteristic value is larger than the simulated time domain characteristic value, obtaining a transmission chain monitoring result through the transmission chain monitoring model in combination with the wind power fan digital twin according to the sound data and the temperature data of the transmission chain and the time domain oscillogram.

Optionally, the step of obtaining the transmission chain monitoring result comprises:

gathering and producing frequency band signals: performing wavelet multi-resolution analysis on the time domain oscillogram through the transmission chain monitoring model to generate a frequency band signal set;

a step of obtaining a fault characteristic frequency value by a great sun step: performing refined spectrum analysis and envelope spectrum analysis on each frequency band signal in the frequency band signal set to obtain a fault characteristic frequency value;

determining a transmission chain monitoring result: and inputting the fault characteristic frequency value into the wind power fan digital twin body for simulation, determining a fault part of the transmission chain, and determining the fault severity according to the fault characteristic frequency value, sound data and temperature data of the transmission chain to obtain a transmission chain monitoring result.

Optionally, the blade monitoring sub-step comprises:

inputting a blade monitoring model: respectively aligning the environmental data, the blade working condition data in the working condition data set and the sound data, the vibration data and the temperature data of the blade according to the time sequence, and inputting the data into the blade monitoring model;

and (3) generating simulated vibration data: generating simulated vibration data by combining the digital twin body of the wind power fan according to the aligned environment data and the aligned working condition data of the blades through the blade monitoring model;

deviation comparison step: calculating a deviation coefficient of the vibration data of the blade and the simulated vibration data through the blade monitoring model, and comparing the deviation coefficient with a preset deviation interval;

time domain feature set extraction step: if the deviation coefficient is not in the preset deviation interval, extracting a time domain feature set of the vibration data of the blade;

blade monitoring step: inputting the time domain feature set into the wind power fan digital twin body, determining a fault part of the blade, and determining the fault severity according to the time domain feature set, the sound data and the temperature data of the blade to obtain a blade monitoring result.

Optionally, the tower monitoring sub-step comprises:

and (3) deformation data calculation: inputting the environment data, the working condition data set, the shaking data and the inclination data of the tower drum into the tower drum monitoring model, and calculating deformation data of the tower drum through the tower drum monitoring model;

and (3) tower barrel monitoring, namely: and acquiring a time domain feature set of the deformation data through the tower cylinder monitoring model, inputting the time domain feature set of the deformation data into the wind power fan digital twin body, and determining the fault position and the fault severity of the tower cylinder to obtain a tower cylinder monitoring result.

In addition, in order to achieve the above object, the present invention further provides a wind power fan monitoring device, including:

the classification module is used for collecting target data through a sensor and a data acquisition unit which are installed in advance when a starting instruction is detected, and classifying the target data to obtain a classification result;

the input module is used for inputting the target data into a corresponding monitoring model according to the classification result, and combining the monitoring model with a pre-established wind power fan digital twin body to obtain a monitoring result;

and the display module is used for displaying the monitoring result based on the wind power fan digital twin body.

Further, the classification module is further configured to:

collecting sound data, vibration data and temperature data of the transmission chain and the blades through the sound, vibration and temperature integrated sensor;

acquiring shaking data of the tower drum through the shaking degree sensor, and acquiring inclination data of the tower drum through the inclination angle sensor;

collecting working condition data sets and environment data of the wind power fan through a data collector, and combining the sound data, the vibration data, the temperature data, the shaking data and the inclination data to obtain target data.

Further, the input module is further configured to:

according to the classification result, inputting the environment data, the transmission chain working condition data in the working condition data set, and the sound data, the vibration data and the temperature data of the transmission chain into the transmission chain monitoring model, and combining the transmission chain monitoring model with a pre-established wind power fan digital twin body to obtain a transmission chain monitoring result;

inputting the environmental data, the blade working condition data in the working condition data set, and the sound data, the vibration data and the temperature data of the blade into the blade monitoring model, and combining the pre-created wind power fan digital twin body through the blade monitoring model to obtain a blade monitoring result;

and inputting the environment data, the working condition data set and the shaking data and the inclination data of the tower drum into the tower drum monitoring model, and combining the tower drum monitoring model with a pre-established wind power fan digital twin body to obtain a tower drum monitoring result.

Further, the input module further comprises a drive chain monitoring module for:

inputting the environmental data, the transmission chain working condition data and the sound data, the vibration data and the temperature data of the transmission chain into the transmission chain monitoring model;

generating a corresponding time domain oscillogram according to the vibration data of the transmission chain through the transmission chain monitoring model, and calculating a time domain characteristic value corresponding to the vibration data of the transmission chain according to the time domain oscillogram;

generating a simulation time domain characteristic value of the transmission chain according to the environment data and the transmission chain working condition data by combining the transmission chain monitoring model with the wind power fan digital twin body, and comparing the time domain characteristic value with the simulation time domain characteristic value;

and if the time domain characteristic value is larger than the simulated time domain characteristic value, obtaining a transmission chain monitoring result by combining the transmission chain monitoring model with the digital twin organism of the wind power fan according to the sound data and the temperature data of the transmission chain and the time domain oscillogram.

Further, the drive train monitoring module is further configured to:

performing wavelet multi-resolution analysis on the time domain oscillogram through the transmission chain monitoring model to generate a frequency band signal set;

performing refined spectrum analysis and envelope spectrum analysis on each frequency band signal in the frequency band signal set to obtain a fault characteristic frequency value;

and inputting the fault characteristic frequency value into the wind power fan digital twin body for simulation, determining a fault part of the transmission chain, and determining the fault severity according to the fault characteristic frequency value, sound data and temperature data of the transmission chain to obtain a transmission chain monitoring result.

Further, the input module further comprises a blade monitoring module for:

respectively aligning the environmental data, the working condition data of the blades in the working condition data set, and the sound data, the vibration data and the temperature data of the blades according to the time sequence, and inputting the data into the blade monitoring model;

generating simulated vibration data by combining the digital twin body of the wind power fan according to the aligned environment data and the aligned working condition data of the blades through the blade monitoring model;

calculating a deviation coefficient of the vibration data of the blade and the simulated vibration data through the blade monitoring model, and comparing the deviation coefficient with a preset deviation interval;

if the deviation coefficient is not in the preset deviation interval, extracting a time domain feature set of the vibration data of the blade;

inputting the time domain feature set into the wind power fan digital twin body, determining a fault part of the blade, and determining the fault severity according to the time domain feature set, the sound data and the temperature data of the blade to obtain a blade monitoring result.

Further, the input module further comprises a tower monitoring module, and the tower monitoring module is configured to:

inputting the environment data, the working condition data set, the shaking data and the inclination data of the tower drum into the tower drum monitoring model, and calculating deformation data of the tower drum through the tower drum monitoring model;

and acquiring a time domain feature set of the deformation data through the tower cylinder monitoring model, inputting the time domain feature set of the deformation data into the wind power fan digital twin body, and determining the fault position and the fault severity of the tower cylinder to obtain a tower cylinder monitoring result.

In addition, in order to achieve the above object, the present invention further provides a wind turbine monitoring system, including: the monitoring method comprises a memory, a processor and a wind power fan monitoring program which is stored on the memory and can run on the processor, wherein the wind power fan monitoring program realizes the steps of the wind power fan monitoring method when being executed by the processor.

In addition, in order to achieve the above object, the present invention further provides a computer readable storage medium, where the computer readable storage medium is a computer readable storage medium, the computer readable storage medium stores a wind turbine monitoring program, and the wind turbine monitoring program, when executed by a processor, implements the steps of the wind turbine monitoring method described above.

The wind power fan monitoring method provided by the invention comprises the following steps: and (3) classification step: when a starting instruction is detected, acquiring target data through a sensor and a data acquisition unit which are installed in advance, and classifying the target data to obtain a classification result; a monitoring step: inputting the target data into a corresponding monitoring model according to the classification result, and combining the monitoring model with a pre-established wind power fan digital twin body to obtain a monitoring result; a display step: and displaying the monitoring result based on the wind power fan digital twin body. According to the invention, target data are collected through the pre-installed sensor and the data collector, the target data are classified and input into the corresponding monitoring model, and the monitoring result is obtained through the corresponding monitoring model and the wind power fan digital twin body, so that the accuracy of abnormity monitoring of the wind power fan is improved.

Drawings

FIG. 1 is a schematic diagram of an apparatus architecture of a hardware operating environment according to an embodiment of the present invention;

FIG. 2 is a schematic flow chart of a wind turbine generator monitoring method according to a first embodiment of the present invention;

FIG. 3 is a schematic flow chart of a wind turbine generator monitoring method according to a second embodiment of the present invention;

FIG. 4 is a schematic flow chart of a third embodiment of a wind turbine monitoring method according to the present invention;

fig. 5 is a schematic flow chart of a wind turbine generator monitoring method according to a fourth embodiment of the present invention.

The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.

Detailed Description

It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention.

As shown in fig. 1, fig. 1 is a schematic device structure diagram of a hardware operating environment according to an embodiment of the present invention.

The device of the embodiment of the invention can be a PC or a server device.

As shown in fig. 1, the apparatus may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, a communication bus 1002. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., a WI-FI interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a storage device separate from the processor 1001.

Those skilled in the art will appreciate that the configuration of the apparatus shown in fig. 1 is not intended to be limiting of the apparatus and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.

As shown in fig. 1, the memory 1005, which is a kind of computer storage medium, may include an operating system, a network communication module, a user interface module, and a wind turbine monitoring program.

The operating system is a program for managing and controlling the portable storage device and software resources, and supports the operation of a network communication module, a user interface module, a wind power fan monitoring program and other programs or software; the network communication module is used for managing and controlling the network interface 1002; the user interface module is used to manage and control the user interface 1003.

In the storage device shown in fig. 1, the storage device calls, through the processor 1001, a wind turbine monitoring program stored in the memory 1005, and performs the operations in the following embodiments of the wind turbine monitoring method.

Based on the hardware structure, the embodiment of the wind power fan monitoring method is provided.

Referring to fig. 2, fig. 2 is a schematic flow chart of a first embodiment of a wind turbine monitoring method according to the present invention, where the method includes:

a monitoring step: according to the classification result, the target data are input into a corresponding monitoring model, and a monitoring result is obtained through the combination of the monitoring model and a pre-established wind power fan digital twin body;

The wind power fan monitoring method of the embodiment is applied to a monitoring system of a wind power generation mechanism, is used for monitoring whether the running state of a wind power fan is abnormal or not, and is described by taking the monitoring system as an example for convenience of description; when a monitoring system detects a starting instruction, sound data, vibration data and temperature data of a transmission chain and blades are collected through a sound, vibration and temperature integrated sensor; acquiring shaking data of a tower drum through a shaking degree sensor, and acquiring inclination data of the tower drum through an inclination angle sensor; collecting a working condition data set and environmental data of the wind power fan through a data collector, combining sound data, vibration data, temperature data, shaking data and inclination data to obtain target data, and classifying the target data to obtain a classification result; the monitoring system inputs the environment data, the transmission chain working condition data in the working condition data set and the sound data, the vibration data and the temperature data of the transmission chain into a transmission chain monitoring model according to the classification result, and combines the pre-created wind power fan digital twin body through the transmission chain monitoring model to obtain a transmission chain monitoring result; inputting the environmental data, the working condition data of the blades in the working condition data set, and the sound data, the vibration data and the temperature data of the blades into a blade monitoring model, and combining the pre-created wind power fan digital twin body through the blade monitoring model to obtain a blade monitoring result; and inputting the environmental data, the working condition data set and the shaking data and the inclination data of the tower into a tower monitoring model, and combining the pre-created wind power fan digital twin body through the tower monitoring model to obtain a tower monitoring result.

When the monitoring system of the embodiment detects a starting instruction, target data are collected through a sensor and a data collector which are installed in advance, and the target data are classified to obtain a classification result; according to the classification result, inputting target data into a corresponding monitoring model, and combining the monitoring model with a pre-established wind power fan digital twin body to obtain a monitoring result; and displaying the monitoring result based on the wind power fan digital twin body. According to the invention, target data are collected through the pre-installed sensor and the data collector, the target data are classified and input into the corresponding monitoring model, and the monitoring result is obtained through the corresponding monitoring model and the wind power fan digital twin body, so that the accuracy of abnormity monitoring of the wind power fan is improved.

The following describes the steps in detail:

in this embodiment, when the monitoring system detects a start instruction, the sensor and the data collector installed in advance are used to collect target data, optionally, the monitoring system may collect the target data through the sensor and the data collector in real time or according to a certain period according to an instruction of a related operator, and after collecting the target data, the monitoring system classifies the target data to obtain a classification result.

Specifically, the step of classifying comprises:

in the step, a monitoring system collects sound data, vibration data and temperature data of a transmission chain through a sound, vibration and temperature integrated sensor arranged in the transmission chain of the wind power fan, and collects sound data, vibration data and temperature data of a blade through a sound, vibration and temperature integrated sensor arranged at the root of the blade of the wind power fan; the transmission chain comprises a main shaft, a gear box and a generator, so that a sound, vibration and temperature integrated sensor is respectively arranged at the front end and the rear end of the main shaft, a sound, vibration and temperature integrated sensor is arranged in the gear box, and a sound, vibration and temperature integrated sensor is arranged in the generator; the wind power fan is provided with three blades generally, so that a sound, vibration and temperature integrated sensor is arranged at the root of each blade; through the integrative sensor of installation sound, vibration and temperature, reduce the quantity of sensor, and then reduce the sensor to the influence of driving chain and blade to through the integrative sensor of sound, vibration and temperature, can gather polytype data, make follow-up accuracy to the analysis of the running state of wind-powered electricity generation fan higher.

A tower data acquisition sub-step: acquiring shaking data of the tower drum through the shaking degree sensor, and acquiring inclination data of the tower drum through the inclination angle sensor;

in the step, the monitoring system acquires shaking data of the tower drum through a shaking degree sensor arranged at the top end of the tower drum, and acquires inclination data of the tower drum through an inclination angle sensor arranged at the top end of the tower drum and an inclination angle sensor arranged at the bottom end of the tower drum;

determine target data sub-step: collecting working condition data sets and environment data of the wind power fan through a data collector, and combining the sound data, the vibration data, the temperature data, the shaking data and the inclination data to obtain target data.

In the step, the monitoring system acquires a working condition data set and environmental data of the wind power fan through the data acquisition unit, and combines sound data, vibration data, temperature data, and shaking data and inclination data of the transmission chain and the blades to obtain target data.

specifically, the monitoring step includes:

a tower barrel monitoring substep: and inputting the environment data, the working condition data set, the shaking data and the inclination data of the tower drum into the tower drum monitoring model, and combining the pre-created wind power fan digital twin body through the tower drum monitoring model to obtain a tower drum monitoring result.

In this embodiment, the monitoring system classifies target data, inputs the target data and the environmental data corresponding to the transmission chain into the transmission chain monitoring model, inputs the target data and the environmental data corresponding to the blades into the blade monitoring model, inputs the target data and the environmental data corresponding to the tower into the tower monitoring model, and combines pre-established wind turbine digital twin bodies through the transmission chain monitoring model, the blade monitoring model and the tower monitoring model to obtain a transmission chain detection result, a blade monitoring result and a tower monitoring result. The digital twin body of the wind power fan is a digital model of the wind power fan created by a digital twin technology, and the digital twin body of the wind power fan contains all parameters and mechanical structures of the wind power fan and can be used for simulating the working state of the wind power fan; the monitoring system processes the corresponding target data by combining the corresponding monitoring model with the wind power fan digital twin body, and because the wind power fan digital twin body can be simulated according to the corresponding data, the data can be analyzed completely instead of manpower, and the accuracy of processing the data is higher than that of manual processing, the labor cost can be reduced, and the accuracy of monitoring the abnormity of a transmission chain, blades and a tower drum of the wind power fan can be improved.

In this embodiment, after obtaining the monitoring result, the monitoring system shows the monitoring result to relevant personnel based on the wind power fan digital twin body, for example: the monitoring system determines a corresponding transmission chain position, a blade position and a tower drum position based on a pre-created wind power fan digital twin body, displays a transmission chain monitoring result in the transmission chain position, displays a blade monitoring result in the blade position and displays a tower drum monitoring result in the tower drum position; furthermore, the monitoring system can also determine the abnormal condition of the wind power fan according to the monitoring result, and display the abnormal part, the fault severity and the like corresponding to the abnormal condition through the digital twin body of the wind power fan. The method has the advantages that relevant personnel can visually and clearly determine the current condition of the wind power fan, the efficiency of determining whether the wind power fan is abnormal or not is improved, and abnormal further deterioration is effectively avoided.

When the monitoring system of the embodiment detects a starting instruction, sound data, vibration data and temperature data of a transmission chain and blades are collected through a sound, vibration and temperature integrated sensor; acquiring shaking data of the tower drum through a shaking degree sensor, and acquiring inclination data of the tower drum through an inclination angle sensor; collecting a working condition data set and environmental data of the wind power fan through a data collector, combining sound data, vibration data, temperature data, shaking data and inclination data to obtain target data, and classifying the target data to obtain a classification result; the monitoring system inputs the environmental data, the working condition data of the transmission chain in the working condition data set and the sound data, the vibration data and the temperature data of the transmission chain into a transmission chain monitoring model according to the classification result, and combines the pre-established wind power fan digital twin body through the transmission chain monitoring model to obtain a transmission chain monitoring result; inputting the environmental data, the working condition data of the blades in the working condition data set, and the sound data, the vibration data and the temperature data of the blades into a blade monitoring model, and combining the pre-created wind power fan digital twin body through the blade monitoring model to obtain a blade monitoring result; and inputting the environmental data, the working condition data set and the shaking data and the inclination data of the tower drum into a tower drum monitoring model, and combining the pre-created wind power fan digital twin body through the tower drum monitoring model to obtain a tower drum monitoring result. The target data are collected through the sensor and the data collector which are installed in advance, the target data are classified and input into the corresponding monitoring model, the monitoring result is obtained through the corresponding monitoring model and the wind power fan digital twin body, and the accuracy of abnormity monitoring of the wind power fan is improved.

Referring to fig. 3, fig. 3 is a schematic flow chart of a wind turbine monitoring method according to a second embodiment of the present invention, and the transmission chain monitoring sub-step includes:

and (3) inputting a transmission chain monitoring model: inputting the environmental data, the transmission chain working condition data and the sound data, the vibration data and the temperature data of the transmission chain into the transmission chain monitoring model;

in the step of inputting the transmission chain monitoring model and the step of calculating the time domain characteristic value, the monitoring system inputs environmental data, transmission chain working condition data, sound data, vibration data and temperature data of the transmission chain into the transmission chain monitoring model, generates a corresponding time domain oscillogram according to the vibration data of the transmission chain through the transmission chain monitoring model, and calculates the time domain characteristic value corresponding to the vibration data of the transmission chain according to the time domain oscillogram; it can be understood that when the transmission chain works, corresponding vibration data can be generated due to the rotation of each mechanical structure, sound data can be generated due to the collision of each mechanical structure, temperature data can be generated due to the friction between each mechanical structure, and the correlation degree of whether the vibration data and the working state of the transmission chain are abnormal is the largest, so that the time domain characteristic value of the vibration data is firstly calculated;

optionally, the time-domain characteristic value includes a dimensional index and a dimensionless index, and the dimensional index includes: peak-to-peak value, mean value, root mean square value and the like, and dimensionless indexes comprise: the monitoring system can calculate one or more indexes of dimensional indexes and dimensionless indexes as time-domain characteristic values of vibration data of the transmission chain through the transmission chain monitoring model.

Preferably, the monitoring system calculates a root mean square value in a dimensional index and a kurtosis and a peak index in a dimensionless index as time-domain characteristic values of vibration data of the drive chain through the drive chain monitoring model, wherein a formula for calculating the root mean square value is as follows:

the formula for calculating the kurtosis is:

wherein,

the formula for calculating the peak index is:

in the above formula, N is the number of sample points in the time domain waveform diagram, x _i The corresponding value for each sample point.

Comparing the characteristic values: generating a simulated time domain characteristic value of the transmission chain according to the environment data and the transmission chain working condition data by combining the transmission chain monitoring model with a wind power fan digital twin body, and comparing the time domain characteristic value with the simulated time domain characteristic value;

in the step, a monitoring system inputs environment data and transmission chain working condition data into a wind power fan digital twin body through a transmission chain monitoring model, the wind power fan digital twin body simulates according to the environment data and the transmission chain working condition data, the condition that a transmission chain of a wind power fan works according to the transmission chain working condition data under the environment data is simulated, simulated vibration data of the transmission chain is obtained, a root mean square value, a kurtosis value and a peak index corresponding to the simulated vibration data are calculated through the transmission chain monitoring model and serve as simulated time domain characteristic values, and the time domain characteristic values are compared with the simulated time domain characteristic values; it should be noted that the process of calculating the root mean square value, the kurtosis and the peak index corresponding to the simulated vibration data is the same as the above process, and is not repeated here; the environment data comprises wind speed, lightning stroke, air temperature, rain, snow and the like, and the simulation is performed through a digital twin body of the wind power fan, so that a simulated time domain characteristic value corresponding to normal vibration data generated when the work is performed according to the working condition data of the transmission chain under the current environment data can be determined, and the accuracy of comparing the time domain characteristic value with the simulated time domain characteristic value is improved.

And (3) obtaining a transmission chain monitoring result: and if the time domain characteristic value is larger than the simulated time domain characteristic value, obtaining a transmission chain monitoring result by combining the transmission chain monitoring model with the digital twin organism of the wind power fan according to the sound data and the temperature data of the transmission chain and the time domain oscillogram.

In the step, after comparing the time domain characteristic value with the simulated time domain characteristic value, if the time domain characteristic value is not larger than the simulated time domain characteristic value, the monitoring system determines that the transmission chain of the current wind power fan is not abnormal; and if the time domain characteristic value is larger than the simulated time domain characteristic value, determining that the transmission chain of the current wind power fan is abnormal, performing wavelet multi-resolution analysis, refined spectrum analysis and envelope spectrum analysis on the time domain oscillogram through a transmission chain monitoring model, and determining the fault position and the fault severity of the transmission chain by combining sound data and temperature data of the transmission chain so as to obtain a transmission chain monitoring result.

Specifically, the step of obtaining the transmission chain monitoring result comprises the following steps:

in this step, the monitoring system performs wavelet multi-resolution analysis on the vibration data of the transmission chain in the time domain oscillogram through the transmission chain monitoring model to generate a frequency band signal set, which can be understood as including a low frequency signal and an intermediate frequency signal; the calculation process for performing wavelet multi-resolution analysis is as follows:

wherein, the monitoring system sets the wavelet fundamental wave as Z (t) in advance, the wavelet fundamental wave is the signal space with limited energy, a is the expansion changeB is a translation variable, the monitoring system adjusts a and b according to different frequency bands, and corresponding wavelet sequences Z of the wavelet fundamental waves to different frequency bands are calculated through the formula _a,b (t)。

Y(a，b)＝∫f(t)Z _a，b (t)dt

The monitoring system generates a frequency band signal set by performing memorability integral operation on the vibration data and wavelet sequences corresponding to different frequency bands according to the formula, so that the vibration data of the transmission chain can be converted into a frequency band signal set comprising a plurality of frequency band signals, more detailed data in the vibration data can be recorded in each frequency band signal, and the analysis accuracy can be improved.

A step of obtaining a fault characteristic frequency value by a great sun step: performing signal reconstruction on each frequency band signal in the frequency band signal set, and performing refined spectrum analysis and envelope spectrum analysis on each frequency band signal subjected to signal reconstruction to obtain a characteristic frequency value of a fault;

in the step, after obtaining a frequency band signal set corresponding to the vibration data, the monitoring system performs signal reconstruction on each frequency band signal in the frequency band signal set, and performs refined spectrum analysis and envelope spectrum analysis on each frequency band signal subjected to signal reconstruction to obtain a fault characteristic frequency value; such as: the formula for signal reconstruction is:

wherein f is ¹ And (t) is a frequency band signal subjected to signal reconstruction, C is a reconstruction constant which is set in a transmission chain monitoring model of the monitoring system in advance, a is a telescopic variable, b is a translation variable, and the monitoring system adjusts a and b according to different frequency bands, so that different frequency band signals can be reconstructed, the reconstructed signal meets the requirements of subsequent refined spectrum analysis and envelope spectrum analysis, and the processing efficiency is improved.

When the monitoring system obtains each reconstructed frequency band signal, performing refined spectrum analysis and envelope spectrum analysis on each frequency band signal; when the refined spectrum analysis is carried out, the monitoring system firstly determines an analysis frequency interval of each frequency band signal, the frequency contained in each frequency band signal is analyzed according to the corresponding analysis frequency interval, when the envelope spectrum analysis is carried out, the monitoring system firstly extracts the envelope spectrum of each frequency band signal, the frequency contained in each frequency band signal is analyzed according to the envelope spectrum, and the fault characteristic frequency value of the vibration data is obtained through the refined spectrum analysis and the envelope spectrum analysis, wherein the fault characteristic frequency value comprises a frequency doubling value and a high-order harmonic frequency value of the vibration data.

Determining a great sun step according to a monitoring result of a transmission chain: and inputting the fault characteristic frequency value into the wind power fan digital twin body for simulation, determining a fault part of the transmission chain, and determining the fault severity according to the fault characteristic frequency value, the sound data and the temperature data of the transmission chain so as to obtain a transmission chain monitoring result.

In this step, after obtaining the fault characteristic frequency value, the monitoring system inputs the fault characteristic frequency value into the wind power fan digital twin body, and the wind power fan digital twin body performs analog work according to the frequency multiplication value and the high-order harmonic frequency value in the fault characteristic frequency value to determine the fault position of the transmission chain, such as: when a supporting part of the transmission chain is loosened, the superposition of frequency multiplication and high-order harmonic waves can occur, and the fault part of the transmission chain can be determined as the supporting part after the digital twin body of the wind power fan is simulated according to the input fault characteristic frequency value;

after the monitoring system determines a fault part, determining the severity of the fault according to the fault characteristic frequency value, the sound data and the temperature data of the transmission chain, such as: the monitoring system carries out non-dimensionalization processing on the fault characteristic frequency value, the sound data and the temperature data of the transmission chain, calculates a fault severity coefficient according to the fault characteristic frequency value, the sound data and the temperature data of the transmission chain which are subjected to the non-dimensionalization processing, and calculates the fault severity coefficient according to the following formula:

where k is the fault severity coefficient, S _i For the sound data of the ith time point subjected to non-dimensionalization processing, W _i F is a value of a fault characteristic frequency subjected to non-dimensionalization, a, b and c are corresponding weight coefficients respectively, and t is a time point of sound data and temperature data. Because the fault severity is related to various data, the fault severity is calculated by integrating the fault characteristic frequency value, the sound data of the transmission chain and the temperature data, and the accuracy of the fault severity is improved.

After the monitoring system calculates the fault severity coefficient, the fault severity coefficient is compared with a preset fault severity coefficient table to determine the severity of the fault, then a transmission chain monitoring result is obtained according to the fault position and the fault severity, the fault position and the fault severity are displayed to related personnel through a wind power fan digital twin body, and when the fault severity is high, alarm processing is carried out simultaneously.

The monitoring system of the embodiment inputs environmental data, transmission chain working condition data, and sound data, vibration data and temperature data of a transmission chain into a transmission chain monitoring model; calculating a time domain characteristic value corresponding to the vibration data of the transmission chain according to the vibration data of the transmission chain through the transmission chain monitoring model; generating a simulation time domain characteristic value of the transmission chain according to the environment data and the transmission chain working condition data by combining the transmission chain monitoring model with the wind power fan digital twin body, and comparing the time domain characteristic value with the simulation time domain characteristic value; and if the time domain characteristic value is larger than the analog time domain characteristic value, obtaining a transmission chain monitoring result by combining the transmission chain monitoring model with the digital twin of the wind power fan according to the sound data and the temperature data of the transmission chain and the fault characteristic frequency value in the time domain oscillogram. The accuracy of the obtained simulated time domain characteristic value is improved by combining the simulation of the wind power fan digital twin, the accuracy of judging whether the transmission chain has faults is further improved, the fault severity is determined by combining sound data, temperature data and a fault characteristic frequency value, and the accuracy of alarming is improved.

Referring to fig. 4, fig. 4 is a schematic flow chart of a wind turbine generator monitoring method according to a third embodiment of the present invention, where the blade monitoring sub-step includes:

inputting a blade monitoring model: respectively aligning the environmental data, the working condition data of the blades in the working condition data set, and the sound data, the vibration data and the temperature data of the blades according to the time sequence, and inputting the data into the blade monitoring model;

in the blade monitoring model input step and the simulated vibration data generation step, after acquiring environment data, blade working condition data in a working condition data set, sound data, vibration data and temperature data of a blade, a monitoring system aligns the environment data, the blade working condition data in the working condition data set, the sound data, the vibration data and the temperature data of the blade according to the time sequence of the acquired data, inputs the aligned environment data and the blade working condition data into a wind power fan digital twin body through the blade monitoring model, performs simulated work based on the generated environment data and the blade working condition data through the wind power fan digital twin body, and records the simulated vibration data of the blade generated during the work; it should be noted that the environmental data include wind speed, lightning strike, air temperature, rain and snow, and are simulated by a digital twin body of the wind turbine, so that simulated vibration data generated when the blade works according to blade working condition data can be determined based on various data under the current environmental data, and the simulated vibration data is vibration data generated when the blade is not abnormal, which is beneficial to improving the accuracy of determining normal vibration data of the blade, and is further beneficial to subsequently judging whether the blade is abnormal.

in the step, after the monitoring system obtains the simulated vibration data of the blade, calculating the deviation coefficient of the vibration data of the blade and the simulated vibration data through a blade monitoring model, and comparing the deviation coefficient with a preset deviation interval; when the deviation interval is preset, the deviation interval is set in the blade monitoring model in advance; the formula for calculating the deviation coefficient is:

wherein A is a deviation coefficient, N is the number of sampling points set in the blade detection model according to experience, and x _n Corresponding frequency value, x, to the nth sampling point in the vibration data of the blade ¹ _n And the frequency value corresponding to the nth sampling point in the blade simulation vibration data. The monitoring system samples N data in the vibration data and the simulated vibration data of the blade respectively according to the number N of the preset sampling points, and calculates the deviation coefficient A of the vibration data and the simulated vibration data of the blade according to the formula. The data of N sampling points are respectively obtained from the vibration data and the simulated vibration data of the blade, all the data in the vibration data and the simulated vibration data do not need to be obtained for calculation, and the calculation efficiency is improved while the accuracy is ensured.

Time domain feature set extraction step: if the deviation coefficient is not within the preset deviation interval, extracting a time domain feature set of the vibration data of the blade;

in the step, if the monitoring system determines that the deviation coefficient is not in the preset deviation interval, performing time-frequency analysis on the vibration data of the blade to obtain a time domain feature set of the vibration data of the blade; such as: the monitoring system is characterized in that the monitoring system is characterized by the following formula:

carrying out time-frequency analysis on the vibration data of the blade to calculate the blade vibrationTime-frequency curve C of dynamic data _x (t, f), wherein t is unit time corresponding to the vibration data, f is the frequency of the vibration data, a is a coefficient, a is generally 0.5, j is an imaginary unit, i is a time shift parameter set in advance, and after the monitoring system obtains a time-frequency curve, the monitoring system performs frequency energy conversion on a unit time signal of the time-frequency curve, so as to obtain a frequency mode and a frequency peak of the vibration data as a time domain feature set.

In the step, after a time domain feature set is obtained by a monitoring system, the time domain feature set is input into a wind power fan digital twin body, and the wind power fan digital twin body carries out simulation work according to a frequency mode and a frequency peak value in the time domain feature set to determine a fault part of a blade; after determining the fault part of the blade, the monitoring system determines the severity of the fault according to the time domain feature set, the sound data and the temperature data of the blade, such as: the monitoring system carries out non-dimensionalization processing on the time domain feature set and the sound data and the temperature data of the transmission chain, calculates a fault severity coefficient according to the non-dimensionalized time domain feature set and the sound data and the temperature data of the transmission chain, and calculates the fault severity coefficient according to the following formula:

where k is the fault severity coefficient, S _i For the sound data at the ith time point subjected to non-dimensionalization processing, W _i The time domain feature set is a time domain feature set, a, b and c are corresponding weight coefficients respectively, and t is the time points of sound data and temperature data. Because the fault severity of the blade is related to various data, the time domain feature set and the transmission are integratedAnd calculating the severity of the fault by using the sound data and the temperature data of the chain, and improving the accuracy of the fault degree.

After the monitoring system calculates the fault severity coefficient, the fault severity coefficient is compared with a preset fault severity coefficient table to determine the severity of the fault, then a blade monitoring result is obtained according to the fault position and the fault severity, the fault position and the fault severity are displayed to related personnel through a wind power fan digital twin body, and when the fault severity is high, warning processing is carried out simultaneously.

The monitoring system of the embodiment simulates by combining with the wind power fan digital twin, improves the accuracy of the obtained simulated vibration data, further improves the accuracy of judging whether the blade has a fault, determines the fault severity of the blade by combining with sound data, temperature data and a time domain feature set, and improves the accuracy of alarming.

Referring to fig. 5, fig. 5 is a schematic flow chart of a wind turbine generator monitoring method according to a fourth embodiment of the present invention, where the tower monitoring substep includes:

a tower drum monitoring step: and acquiring the time domain feature set of the deformation data through the tower cylinder monitoring model, inputting the time domain feature set of the deformation data into the wind power fan digital twin body, and determining the fault part and the fault severity of the tower cylinder to obtain a tower cylinder monitoring result.

In the step of calculating the deformation data and the step of monitoring the tower drum, the monitoring system inputs the environmental data, the working condition data set, the shaking data and the inclination data of the tower drum into a tower drum monitoring model, and the deformation data of the tower drum is calculated according to the data through the tower drum monitoring model; such as: the tower barrel monitoring model calculates deformation data of a tower barrel according to the following formula:

x(t)＝(m+nt)h ^r +ch ^s cosωt

omega is the vibration frequency of a tower drum, and is obtained by calculation of a tower drum monitoring system according to shaking data and inclination data of the tower drum, c is a dynamic deformation coefficient, s is a dynamic deformation index, m is a static deformation coefficient, n is a quasi-static deformation coefficient, c, s, m and n can be obtained by calculation of the tower drum monitoring system according to environmental data and working condition data of the tower drum, r is a constant, and h is the height of the tower drum. The monitoring system calculates deformation data of the tower drum through the tower drum monitoring model, further obtains a deformation curve of the tower drum, obtains a time domain feature set of the deformation curve through the tower drum monitoring model, inputs the time domain feature set into the wind power fan digital twin body, simulates according to the time domain feature set through the wind power fan digital twin body, determines a fault position and fault severity of the tower drum, further obtains a tower drum monitoring result, and further shows the fault position and the fault severity to relevant personnel through the wind power fan digital twin body and gives an alarm.

According to the monitoring system, the deformation data of the tower drum is calculated by combining the tower drum monitoring model with the environmental data, the tower drum working condition data set, the shaking data and the inclination data of the tower drum, and the simulation is performed by combining the digital twin body of the wind power fan according to the time domain characteristics of the deformation data, so that the accuracy of judging whether the tower drum has faults is improved.

The invention also provides a wind power fan monitoring device. The wind power fan monitoring device of the invention comprises:

the classification module is used for collecting target data through a sensor and a data collector which are installed in advance when a starting instruction is detected, and classifying the target data to obtain a classification result;

Further, the classification module is further configured to:

collecting a working condition data set and environment data of the wind power fan through a data collector, and combining the sound data, the vibration data, the temperature data, the shaking data and the inclination data to obtain target data.

Further, the input module is further configured to:

according to the classification result, inputting the environment data, the transmission chain working condition data in the working condition data set, and the sound data, vibration data and temperature data of the transmission chain into the transmission chain monitoring model, and combining the transmission chain monitoring model with a pre-created wind power fan digital twin body to obtain a transmission chain monitoring result;

and inputting the environment data, the working condition data set, the shaking data and the inclination data of the tower drum into the tower drum monitoring model, and combining the pre-created wind power fan digital twin body through the tower drum monitoring model to obtain a tower drum monitoring result.

generating a simulation time domain characteristic value of the transmission chain according to the environment data, the transmission chain working condition data, the sound data and the temperature data of the transmission chain by combining the transmission chain monitoring model with the wind power fan digital twin body;

if the time domain characteristic value is larger than the analog time domain characteristic value, generating a corresponding time domain oscillogram according to the time domain oscillogram;

and obtaining a transmission chain monitoring result through the transmission chain monitoring model according to the time domain oscillogram and the wind power fan digital twin body.

Further, the drive train monitoring module is further configured to:

performing signal reconstruction on each frequency band signal in the frequency band signal set, and performing refined spectrum analysis and envelope spectrum analysis on each frequency band signal subjected to signal reconstruction to obtain a fault characteristic frequency value;

and inputting the fault characteristic frequency value into the wind power fan digital twin body for simulation, and determining the fault part and the fault severity of the transmission chain to obtain a transmission chain monitoring result.

Further, the input module further comprises a blade monitoring module for:

generating simulated vibration data by the blade monitoring model according to the aligned environment data, the aligned blade working condition data, the aligned sound data and the aligned temperature data of the blades and combining with a wind power fan digital twin body;

if the deviation coefficient is not in the preset deviation interval, extracting a time domain feature set of the vibration data of the blade, inputting the time domain feature set into the wind power fan digital twin body, and determining the fault position and the fault severity of the blade to obtain a blade monitoring result.

The invention further provides a wind power fan monitoring system.

Wind-powered electricity generation fan monitoring system includes: the monitoring method comprises a memory, a processor and a wind power fan monitoring program which is stored on the memory and can run on the processor, wherein the wind power fan monitoring program realizes the steps of the wind power fan monitoring method when being executed by the processor.

The method implemented when the wind turbine monitoring program running on the processor is executed may refer to each embodiment of the wind turbine monitoring method of the present invention, and details are not described here.

The invention also provides a computer readable storage medium.

The computer readable storage medium stores a wind turbine monitoring program, and the wind turbine monitoring program, when executed by the processor, implements the steps of the wind turbine monitoring method described above.

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrases "comprising one of 8230; \8230;" 8230; "does not exclude the presence of additional like elements in a process, method, article, or system that comprises the element.

The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.

Through the description of the foregoing embodiments, it is clear to those skilled in the art that the method of the foregoing embodiments may be implemented by software plus a necessary general hardware platform, and certainly may also be implemented by hardware, but in many cases, the former is a better implementation. Based on such understanding, the technical solution of the present invention essentially or contributing to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (such as a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.

The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention, and all equivalent structures or equivalent processes performed by the present specification and the attached drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.

Claims

1. A wind power fan monitoring method is characterized by comprising the following steps:

and (4) classification: when a starting instruction is detected, acquiring target data through a sensor and a data acquisition unit which are installed in advance, and classifying the target data to obtain a classification result;

2. The wind turbine monitoring method of claim 1, wherein the sensor comprises: install sound, vibration and temperature integral type sensor in the driving chain of wind-powered electricity generation fan, install the sound, vibration and temperature integral type sensor of the blade root of wind-powered electricity generation fan, install shake degree sensor and the angular transducer on the tower section of thick bamboo top of wind-powered electricity generation fan and install the angular transducer of tower section of thick bamboo bottom, categorised step includes:

a transmission chain and blade data acquisition sub-step: collecting sound data, vibration data and temperature data of the transmission chain and the blades through the sound, vibration and temperature integrated sensor;

3. The wind turbine generator monitoring method of claim 2, wherein the monitoring model comprises: drive chain monitoring model, blade monitoring model and tower section of thick bamboo monitoring model, the monitoring step includes:

drive chain monitoring substep: according to the classification result, inputting the environment data, the transmission chain working condition data in the working condition data set, and the sound data, vibration data and temperature data of the transmission chain into the transmission chain monitoring model, and combining the transmission chain monitoring model with a pre-created wind power fan digital twin body to obtain a transmission chain monitoring result;

4. The wind turbine generator monitoring method of claim 3, wherein the drive train monitoring substep comprises:

5. The wind turbine generator monitoring method of claim 4, wherein the step of obtaining a drive chain monitoring result comprises:

a frequency band signal collection production great sun step: performing wavelet multi-resolution analysis on the time domain oscillogram through the transmission chain monitoring model to generate a frequency band signal set;

a fault characteristic frequency value is obtained in a great sun step: performing refined spectrum analysis and envelope spectrum analysis on each frequency band signal in the frequency band signal set to obtain a fault characteristic frequency value;

determining a great sun step according to a monitoring result of a transmission chain: and inputting the fault characteristic frequency value into the wind power fan digital twin body for simulation, determining a fault part of the transmission chain, and determining the fault severity according to the fault characteristic frequency value, sound data and temperature data of the transmission chain to obtain a transmission chain monitoring result.

6. The wind turbine generator monitoring method of claim 3, wherein the blade monitoring substep comprises:

and (3) inputting a blade monitoring model, namely: respectively aligning the environmental data, the working condition data of the blades in the working condition data set, and the sound data, the vibration data and the temperature data of the blades according to the time sequence, and inputting the data into the blade monitoring model;

7. The wind turbine monitoring method of claim 3, wherein the tower monitoring substep comprises:

and (3) deformation data calculation step: inputting the environment data, the working condition data set, the shaking data and the inclination data of the tower drum into the tower drum monitoring model, and calculating deformation data of the tower drum through the tower drum monitoring model;

8. The utility model provides a wind-powered electricity generation fan monitoring devices which characterized in that, wind-powered electricity generation fan monitoring devices includes:

9. The utility model provides a wind-powered electricity generation fan monitoring system which characterized in that, wind-powered electricity generation fan monitoring system includes: a memory, a processor and a wind turbine monitoring program stored on the memory and executable on the processor, the wind turbine monitoring program when executed by the processor implementing the steps of the wind turbine monitoring method as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a wind turbine monitoring program, which when executed by a processor implements the steps of the wind turbine monitoring method according to any one of claims 1 to 7.